Streetchange: How new technologies are identifying and mapping neighborhood improvements

July 7, 2017
By Doug Gavel

Many communities in Boston, New York and other U.S. cities have seen dramatic physical improvements in recent years. Fueled by high housing costs, an improving economy and baby boomers moving to urban areas, many urban neighborhoods that were once perceived as down-and-out are now considered up-and-coming places to live. The challenge has come in identifying the next neighborhoods to improve.

In a paper published July 6 in Proceedings of the National Academy of Sciences, a group of researchers based at Harvard and MIT demonstrate how new computer vision technology can provide answers.

Using algorithms to analyze 2007 and 2014 Google Street View images of more than 1.6 million street blocks in five U.S. cities, the research team was able to better understand the key demographic and economic characteristics common to neighborhoods that experience significant physical improvements over time. 

They articulate three important findings:

  • Both education and population density predict improvements in neighborhood infrastructure, in support of theories of human capital agglomeration.
  • Neighborhoods with better initial appearances experience more substantial upgrading, as predicted by the tipping theory of urban change.
  • More improvements in neighborhoods are observed closer to both city centers and other physically attractive neighborhoods, in agreement with the invasion theory of urban sociology.

The researchers posit that the metric they developed, called Streetchange, may become a valuable tool for urban planners and others as they determine the best ways to help promote neighborhood renewal in the future. 

“This work should be of interest to policymakers, urban planners, and social scientists,” the authors suggest. “Policymakers can use these tools to understand the impact of policies on the evolution of private and public infrastructure. Urban planners can use Streetchange and its underlying technology to study the impact of urban design on neighborhood change. And social scientists will be able to improve their understanding of the relationship between the socioeconomic composition of neighborhoods and the built environment.”

The article is authored by Nikhil Naik, Scott Duke Kominers, Ramesh Raskar, Edward L. Glaeser and Cesar A. Hidalgo. Glaeser is the Fred and Eleanor Glimp Professor of Economics at Harvard Kennedy School (HKS). 

Edward Glaeser is the Fred and Eleanor Glimp Professor of Economics at Harvard University. 


John F. Kennedy School of Government 79 John F. Kennedy Street
Cambridge, MA 02138
617-495-1100 Get Directions Visit Contact Page